title://h1[@class="title"] body://main[1] date: //div[contains(concat(' ',normalize-space(@class),' '),' author ')]//time/@datetime author: //div[contains(concat(' ',normalize-space(@class),' '),' author ')]//a[@class='journalist'] single_page_link: //link[@rel="canonical"] strip_id_or_class: news__body__right strip_id_or_class: news__heading__top__kicker strip_id_or_class: page-title strip_id_or_class: news__heading__center strip_id_or_class: splitter strip_id_or_class: engagement-bar-wrapper strip_id_or_class: read-also strip_id_or_class: newsletter-form strip_id_or_class: paywall-login strip_id_or_class: paywall-message strip_id_or_class: paywall_no_variance strip: //button # prevent wallabag from tinyfying paragraphs find_string: class="container replace_string: class="foo_cntr prune: no tidy: no ### wallabag only ### do NOT provide your credentials here, they must be stored in wallabag's UI wrap_in(blockquote): //aside[contains(@class, 'highlight')] requires_login: yes login_uri: https://www.mediapart.fr/login_check login_username_field: email login_password_field: password login_extra_fields: formulaire_action="/login_check" login_extra_fields: op=Se+connecter not_logged_in_xpath: //body[contains(@class,"not-logged-in")] test_url: https://www.mediapart.fr/journal/france/170116/le-site-slatefr-est-passe-entre-les-mains-du-cac-40